© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11773
    Prev
    Next
    INDEX
    Explanations

    personal contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    personal and personalized concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.71
     အ
    0.66
    خ
    0.64
    ಮ
    0.64
     anglais
    0.62
    kker
    0.62
    美國
    0.61
    kosten
    0.61
    Су
    0.60
    F
    0.60
    POSITIVE LOGITS
     personal
    1.11
     व्यक्तिगत
    1.04
     personales
    1.03
    personal
    1.02
    个人
    1.01
     pessoais
    1.01
     Personal
    1.00
     personnelle
    1.00
     PERSONAL
    1.00
     προσωπ
    1.00
    Activations Density 0.261%

    No Known Activations